GPT-3 zero-shot models flag social norm violations across two large datasets
ArtificialOther · x · 2026-09-24
A Scientific Reports paper by Yair Neuman and Yochai Cohen presents a novel approach to identifying social norm violations using GPT-3, zero-shot classification, and automatic rule discovery to build simple predictive models grounded in psychological knowledge.
- Tested on two massive datasets with significant predictive performance
- Shows even complex social situations can be functionally analyzed with modern computational tools
- Open access, published May 2023, with 13k accesses and 19 citations
More from Research
- VoiceArena launches Diarization Bench: 12 systems, NVIDIA Nemotron 3 leads at 14.72% DER — rohanpaul_ai · 2026-09-24
- Berkeley team trains 2.3B MoE Hybrid Mamba matching Llama-3.2-3B with <1% of pretraining FLOPs — berkeley_ai · 2026-09-24
- Why GPT-6's rumored recurrent-depth architecture could change inference economics — panic_in_the_galaxy · 2026-09-24
- An AUC 0.62 classifier cut 65,578 candidates to 145 DFT runs and found 6 new discoveries — bravo_abad · 2026-09-24
- Agentic Optimisation: what's fundamentally new for vision in the agent era — _krishna_murthy · 2026-09-24
- Google's WeatherNext 3 reads raw satellite data, cuts short-range temperature error up to 40% — anselm · 2026-09-24